Console using std::string. Added utf8-cpp dependency.

CMakeLists.txt

@@ -23,7 +23,7 @@ endif()
 
 # Include directories
 include_directories ("${PROJECT_SOURCE_DIR}/include")
-include_directories ("${PROJECT_SOURCE_DIR}/src/deps")
+include_directories (SYSTEM "${PROJECT_SOURCE_DIR}/src/deps")
 include_directories ("${PROJECT_BINARY_DIR}")
 
 # Include External Modules

ChangeLog.md

@@ -10,6 +10,8 @@
     * Added API to Font to draw strings centered
     * Folder sorts its items alphabetically
     * Press dot key in Menu to see hidden files and folders
+    * Console is now using std::string instead of char *
+    * Added utf8-cpp dependency to allow Console to delete multi-byte chars
 
     [ 20140809 ]
     * Script Unit Test brings it’s own scripts to test

README.md

@@ -177,3 +177,5 @@ See the respective files in `cmake` for their licensing.
 
 The [clibs/commander](https://github.com/clibs/commander) dependency is Copyright (c) 2012 TJ Holowaychuk (tj@vision-media.ca) and licensed under the [MIT License](http://opensource.org/licenses/MIT).
 
+The included [utf8-cpp](http://utfcpp.sourceforge.net) headers are Copyright (c) 2006 Nemanja Trifunovic. See the files in src/deps/utf8-cpp/ for informations about the license used.
+

TODO.md

@@ -21,9 +21,7 @@
 
 ## Future Features
 
-* File system utility layer, so mixed-case on case-sensitive filesystems is working transparently
 * Add ability to play the FMVs. Format? VLC can play them!
 * Cut TGA image reader, currently only used for menu background?!
     * Need useful, always available image writer alternative for screenshots then
-* When cutscene rendering is working, use TR4/5 style menu?
 

include/Console.h

@@ -8,6 +8,7 @@
 #ifndef _CONSOLE_H_
 #define _CONSOLE_H_
 
+#include <string>
 #include <vector>
 
 /*!
@@ -21,11 +22,6 @@ public:
      */
     Console();
 
-    /*!
-     * \brief Deconstructs an object of Console
-     */
-    ~Console();
-
     void setVisible(bool visible);
 
     bool isVisible();
@@ -45,14 +41,13 @@ private:
     void moveInHistory(bool up);
 
     bool mVisible;
-    char *mInputBuffer;
-    size_t mInputBufferPointer;
-    char *mPartialInput;
-    std::vector<char *> mHistory;
+    std::string mInputBuffer;
+    std::string mPartialInput;
+    std::vector<std::string> mHistory;
 
     size_t mHistoryPointer;
-    std::vector<char *> mCommandHistory;
-    char *mUnfinishedInput;
+    std::vector<std::string> mCommandHistory;
+    std::string mUnfinishedInput;
 
     unsigned int mLineOffset;
 };

src/Console.cpp

@@ -6,50 +6,22 @@
  */
 
 #include <iostream>
-#include <cstring>
 
 #include "global.h"
 #include "Font.h"
 #include "OpenRaider.h"
+#include "utf8-cpp/utf8.h"
 #include "utils/strings.h"
 #include "utils/time.h"
 #include "Window.h"
 #include "Console.h"
 
-#define INPUT_BUFFER_SIZE 255
-
 Console::Console() {
     mVisible = false;
-    mInputBuffer = new char[INPUT_BUFFER_SIZE + 1];
-    mInputBuffer[INPUT_BUFFER_SIZE] = '\0';
-    mInputBufferPointer = 0;
-    mPartialInput = NULL;
     mHistoryPointer = 0;
-    mUnfinishedInput = NULL;
     mLineOffset = 0;
 }
 
-Console::~Console() {
-    delete [] mInputBuffer;
-    mInputBuffer = NULL;
-
-    delete [] mPartialInput;
-    mPartialInput = NULL;
-
-    delete [] mUnfinishedInput;
-    mUnfinishedInput = NULL;
-
-    while (mHistory.size() > 0) {
-        delete [] mHistory.back();
-        mHistory.pop_back();
-    }
-
-    while (mCommandHistory.size() > 0) {
-        delete [] mCommandHistory.back();
-        mCommandHistory.pop_back();
-    }
-}
-
 void Console::setVisible(bool visible) {
     mVisible = visible;
     getWindow().setTextInput(mVisible);
@@ -66,78 +38,76 @@ void Console::print(const char *s, ...) {
     va_end(args);
 
     if (tmp != NULL) {
-        mHistory.push_back(tmp);
+        mHistory.push_back(std::string(tmp));
 #ifdef DEBUG
         std::cout << tmp << std::endl;
 #endif
     }
+
+    delete [] tmp;
 }
 
-#define LINE_GEOMETRY(window) unsigned int firstLine = 35; \
-        unsigned int lastLine = (window.getHeight() / 2) - 55; \
-        unsigned int inputLine = (window.getHeight() / 2) - 30; \
-        unsigned int lineSteps = 20; \
-        unsigned int lineCount = (lastLine - firstLine + lineSteps) / lineSteps; \
-        while (((lineCount * lineSteps) + firstLine) < inputLine) { \
-            lineSteps++; \
-            lineCount = (lastLine - firstLine + lineSteps) / lineSteps; \
-        }
+#define LINE_GEOMETRY(window) \
+    unsigned int firstLine = 35; \
+    unsigned int lastLine = (window.getHeight() / 2) - 55; \
+    unsigned int inputLine = (window.getHeight() / 2) - 30; \
+    unsigned int lineSteps = 20; \
+    unsigned int lineCount = (lastLine - firstLine + lineSteps) / lineSteps; \
+    while (((lineCount * lineSteps) + firstLine) < inputLine) { \
+        lineSteps++; \
+        lineCount = (lastLine - firstLine + lineSteps) / lineSteps; \
+    }
 
 void Console::display() {
-    if (mVisible) {
-        // Calculate line drawing geometry
-        // Depends on window height, so recalculate every time
-        LINE_GEOMETRY(getWindow());
-
-        // Draw half-transparent *overlay*
-        glColor4f(0.0f, 0.0f, 0.0f, 0.75f);
-        glDisable(GL_TEXTURE_2D);
-        glRecti(0, 0, getWindow().getWidth(), getWindow().getHeight() / 2);
-        glEnable(GL_TEXTURE_2D);
-
-        unsigned long scrollIndicator;
-        if (mHistory.size() > lineCount) {
-            scrollIndicator = (mHistory.size() - lineCount - mLineOffset) * 100 / (mHistory.size() - lineCount);
-        } else {
-            scrollIndicator = 100;
-            mLineOffset = 0;
-        }
+    if (!mVisible)
+        return;
 
-        getFont().drawText(10, 10, 0.70f, BLUE,
-                "%s uptime %lus scroll %d%%", VERSION, systemTimerGet() / 1000, scrollIndicator);
+    // Calculate line drawing geometry
+    // Depends on window height, so recalculate every time
+    LINE_GEOMETRY(getWindow());
 
-        // Draw output log
-        long end = lineCount;
-        long drawOffset = 0;
-        long historyOffset = 0;
-        if (mHistory.size() < lineCount) {
-            end = mHistory.size();
-            drawOffset = lineCount - mHistory.size();
-        } else if (lineCount < mHistory.size()) {
-            historyOffset = mHistory.size() - lineCount;
-        }
-        for (int i = 0; i < end; i++) {
-            getFont().drawText(10, (unsigned int)((i + drawOffset) * lineSteps) + firstLine,
-                    0.75f, BLUE, "%s", mHistory[i + historyOffset - mLineOffset]);
-        }
+    // Draw half-transparent *overlay*
+    glColor4f(0.0f, 0.0f, 0.0f, 0.75f);
+    glDisable(GL_TEXTURE_2D);
+    glRecti(0, 0, getWindow().getWidth(), getWindow().getHeight() / 2);
+    glEnable(GL_TEXTURE_2D);
 
-        // Draw current input
-        if ((mInputBufferPointer > 0) && (mInputBuffer[0] != '\0')) {
-            getFont().drawText(10, inputLine, 0.75f, BLUE, "> %s", mInputBuffer);
-        } else {
-            getFont().drawText(10, inputLine, 0.75f, BLUE, ">");
-        }
+    unsigned long scrollIndicator;
+    if (mHistory.size() > lineCount) {
+        scrollIndicator = (mHistory.size() - lineCount - mLineOffset) * 100 / (mHistory.size() - lineCount);
+    } else {
+        scrollIndicator = 100;
+        mLineOffset = 0;
+    }
 
-        //! \todo display the current mPartialInput. The UTF-8 segfaults SDL-TTF, somehow?
+    getFont().drawText(10, 10, 0.70f, BLUE,
+            "%s uptime %lus scroll %d%%", VERSION, systemTimerGet() / 1000, scrollIndicator);
+
+    // Draw output log
+    long end = lineCount;
+    long drawOffset = 0;
+    long historyOffset = 0;
+    if (mHistory.size() < lineCount) {
+        end = mHistory.size();
+        drawOffset = lineCount - mHistory.size();
+    } else if (lineCount < mHistory.size()) {
+        historyOffset = mHistory.size() - lineCount;
+    }
+    for (int i = 0; i < end; i++) {
+        getFont().drawText(10, (unsigned int)((i + drawOffset) * lineSteps) + firstLine,
+                0.75f, BLUE, "%s", mHistory[i + historyOffset - mLineOffset].c_str());
     }
+
+    // Draw current input
+    getFont().drawText(10, inputLine, 0.75f, BLUE, "> %s", (mInputBuffer + mPartialInput).c_str());
 }
 
 void Console::handleKeyboard(KeyboardButton key, bool pressed) {
     if (pressed && (key == enterKey)) {
         // Execute entered command
-        if ((mInputBufferPointer > 0) && (mInputBuffer[0] != '\0')) {
-            print("> %s", mInputBuffer);
-            mCommandHistory.push_back(bufferString("%s", mInputBuffer));
+        if (mInputBuffer.length() > 0) {
+            print("> %s", mInputBuffer.c_str());
+            mCommandHistory.push_back(mInputBuffer.c_str());
             int error = getOpenRaider().command(mInputBuffer);
             if (error != 0) {
                 print("Error Code: %d", error);
@@ -147,21 +117,16 @@ void Console::handleKeyboard(KeyboardButton key, bool pressed) {
         }
 
         // Clear partial and input buffer
-        mInputBufferPointer = 0;
-        mInputBuffer[0] = '\0';
-        if (mPartialInput != NULL) {
-            delete [] mPartialInput;
-            mPartialInput = NULL;
-        }
-
+        mInputBuffer = "";
+        mPartialInput = "";
         mHistoryPointer = 0;
     }
 
-    //! \fixme only deleting the last byte is not valid for non-ASCII UTF-8 strings
     if (pressed && (key == backspaceKey)) {
-        if (mInputBufferPointer > 0) {
-            mInputBufferPointer--;
-            mInputBuffer[mInputBufferPointer] = '\0';
+        if ((mPartialInput.length() == 0)
+                && (mInputBuffer.length() > 0)) {
+            utf8::iterator<std::string::iterator> it(mInputBuffer.end(), mInputBuffer.begin(), mInputBuffer.end());
+            mInputBuffer.erase((--it).base(), mInputBuffer.end());
         }
     }
 
@@ -178,7 +143,7 @@ void Console::moveInHistory(bool up) {
         if (mHistoryPointer < mCommandHistory.size()) {
             mHistoryPointer++;
             if (mHistoryPointer == 1) {
-                mUnfinishedInput = bufferString("%s", mInputBuffer);
+                mUnfinishedInput = mInputBuffer;
             }
         } else {
             return;
@@ -191,17 +156,13 @@ void Console::moveInHistory(bool up) {
     }
 
     if ((mHistoryPointer > 0) && (mHistoryPointer <= mCommandHistory.size())) {
-        strcpy(mInputBuffer, mCommandHistory[mCommandHistory.size() - mHistoryPointer]);
-        mInputBufferPointer = strlen(mInputBuffer);
+        mInputBuffer = mCommandHistory[mCommandHistory.size() - mHistoryPointer];
     } else {
-        if (mUnfinishedInput != NULL) {
-            strcpy(mInputBuffer, mUnfinishedInput);
-            mInputBufferPointer = strlen(mInputBuffer);
-            delete [] mUnfinishedInput;
-            mUnfinishedInput = NULL;
+        if (mUnfinishedInput.length() > 0) {
+            mInputBuffer = mUnfinishedInput;
+            mUnfinishedInput = "";
         } else {
-            mInputBuffer[0] = '\0';
-            mInputBufferPointer = 0;
+            mInputBuffer = "";
         }
     }
 }
@@ -213,28 +174,17 @@ void Console::handleText(char *text, bool notFinished) {
     if (!notFinished) {
         // Finished entering character
         // delete previous partial character, if present
-        if (mPartialInput != NULL) {
-            delete [] mPartialInput;
-        }
+        mPartialInput = "";
 
         //! \fixme Temporary hack filtering the console activation key
         if (text[0] == '`')
             return;
 
         // Append new input to buffer
-        size_t length = strlen(text);
-        if (length > 0) {
-            if (((INPUT_BUFFER_SIZE - mInputBufferPointer) < length)) {
-                print("Console input buffer overflowed! (> %d)", INPUT_BUFFER_SIZE);
-                return;
-            }
-            strcpy((mInputBuffer + mInputBufferPointer), text);
-            mInputBufferPointer += length;
-            mInputBuffer[mInputBufferPointer] = '\0';
-        }
+        mInputBuffer += text;
     } else {
         // Partial character received
-        mPartialInput = bufferString("%s", text);
+        mPartialInput = text;
     }
 }
 

src/deps/utf8-cpp/utf8.h

@@ -0,0 +1,34 @@
+// Copyright 2006 Nemanja Trifunovic
+
+/*
+Permission is hereby granted, free of charge, to any person or organization
+obtaining a copy of the software and accompanying documentation covered by
+this license (the "Software") to use, reproduce, display, distribute,
+execute, and transmit the Software, and to prepare derivative works of the
+Software, and to permit third-parties to whom the Software is furnished to
+do so, all subject to the following:
+
+The copyright notices in the Software and this entire statement, including
+the above license grant, this restriction and the following disclaimer,
+must be included in all copies of the Software, in whole or in part, and
+all derivative works of the Software, unless such copies or derivative
+works are solely in the form of machine-executable object code generated by
+a source language processor.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE, TITLE AND NON-INFRINGEMENT. IN NO EVENT
+SHALL THE COPYRIGHT HOLDERS OR ANYONE DISTRIBUTING THE SOFTWARE BE LIABLE
+FOR ANY DAMAGES OR OTHER LIABILITY, WHETHER IN CONTRACT, TORT OR OTHERWISE,
+ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER
+DEALINGS IN THE SOFTWARE.
+*/
+
+
+#ifndef UTF8_FOR_CPP_2675DCD0_9480_4c0c_B92A_CC14C027B731
+#define UTF8_FOR_CPP_2675DCD0_9480_4c0c_B92A_CC14C027B731
+
+#include "utf8/checked.h"
+#include "utf8/unchecked.h"
+
+#endif // header guard

src/deps/utf8-cpp/utf8/checked.h

@@ -0,0 +1,323 @@
+// Copyright 2006 Nemanja Trifunovic
+
+/*
+Permission is hereby granted, free of charge, to any person or organization
+obtaining a copy of the software and accompanying documentation covered by
+this license (the "Software") to use, reproduce, display, distribute,
+execute, and transmit the Software, and to prepare derivative works of the
+Software, and to permit third-parties to whom the Software is furnished to
+do so, all subject to the following:
+
+The copyright notices in the Software and this entire statement, including
+the above license grant, this restriction and the following disclaimer,
+must be included in all copies of the Software, in whole or in part, and
+all derivative works of the Software, unless such copies or derivative
+works are solely in the form of machine-executable object code generated by
+a source language processor.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE, TITLE AND NON-INFRINGEMENT. IN NO EVENT
+SHALL THE COPYRIGHT HOLDERS OR ANYONE DISTRIBUTING THE SOFTWARE BE LIABLE
+FOR ANY DAMAGES OR OTHER LIABILITY, WHETHER IN CONTRACT, TORT OR OTHERWISE,
+ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER
+DEALINGS IN THE SOFTWARE.
+*/
+
+
+#ifndef UTF8_FOR_CPP_CHECKED_H_2675DCD0_9480_4c0c_B92A_CC14C027B731
+#define UTF8_FOR_CPP_CHECKED_H_2675DCD0_9480_4c0c_B92A_CC14C027B731
+
+#include "core.h"
+#include <stdexcept>
+
+namespace utf8
+{
+    // Exceptions that may be thrown from the library functions.
+    class invalid_code_point : public ::std::exception {
+        uint32_t cp;
+    public:
+        invalid_code_point(uint32_t _cp) : cp(_cp) {}
+        virtual const char* what() const noexcept { return "Invalid code point"; }
+        uint32_t code_point() const {return cp;}
+    };
+
+    class invalid_utf8 : public ::std::exception {
+        uint8_t u8;
+    public:
+        invalid_utf8 (uint8_t u) : u8(u) {}
+        virtual const char* what() const noexcept { return "Invalid UTF-8"; }
+        uint8_t utf8_octet() const {return u8;}
+    };
+
+    class invalid_utf16 : public ::std::exception {
+        uint16_t u16;
+    public:
+        invalid_utf16 (uint16_t u) : u16(u) {}
+        virtual const char* what() const noexcept { return "Invalid UTF-16"; }
+        uint16_t utf16_word() const {return u16;}
+    };
+
+    class not_enough_room : public ::std::exception {
+    public:
+        virtual const char* what() const noexcept { return "Not enough space"; }
+    };
+
+    /// The library API - functions intended to be called by the users
+
+    template <typename octet_iterator>
+    octet_iterator append(uint32_t cp, octet_iterator result)
+    {
+        if (!utf8::internal::is_code_point_valid(cp))
+            throw invalid_code_point(cp);
+
+        if (cp < 0x80)                        // one octet
+            *(result++) = static_cast<uint8_t>(cp);
+        else if (cp < 0x800) {                // two octets
+            *(result++) = static_cast<uint8_t>((cp >> 6)            | 0xc0);
+            *(result++) = static_cast<uint8_t>((cp & 0x3f)          | 0x80);
+        }
+        else if (cp < 0x10000) {              // three octets
+            *(result++) = static_cast<uint8_t>((cp >> 12)           | 0xe0);
+            *(result++) = static_cast<uint8_t>(((cp >> 6) & 0x3f)   | 0x80);
+            *(result++) = static_cast<uint8_t>((cp & 0x3f)          | 0x80);
+        }
+        else {                                // four octets
+            *(result++) = static_cast<uint8_t>((cp >> 18)           | 0xf0);
+            *(result++) = static_cast<uint8_t>(((cp >> 12) & 0x3f)  | 0x80);
+            *(result++) = static_cast<uint8_t>(((cp >> 6) & 0x3f)   | 0x80);
+            *(result++) = static_cast<uint8_t>((cp & 0x3f)          | 0x80);
+        }
+        return result;
+    }
+
+    template <typename octet_iterator, typename output_iterator>
+    output_iterator replace_invalid(octet_iterator start, octet_iterator end, output_iterator out, uint32_t replacement)
+    {
+        while (start != end) {
+            octet_iterator sequence_start = start;
+            internal::utf_error err_code = utf8::internal::validate_next(start, end);
+            switch (err_code) {
+                case internal::UTF8_OK :
+                    for (octet_iterator it = sequence_start; it != start; ++it)
+                        *out++ = *it;
+                    break;
+                case internal::NOT_ENOUGH_ROOM:
+                    throw not_enough_room();
+                case internal::INVALID_LEAD:
+                    out = utf8::append (replacement, out);
+                    ++start;
+                    break;
+                case internal::INCOMPLETE_SEQUENCE:
+                case internal::OVERLONG_SEQUENCE:
+                case internal::INVALID_CODE_POINT:
+                    out = utf8::append (replacement, out);
+                    ++start;
+                    // just one replacement mark for the sequence
+                    while (start != end && utf8::internal::is_trail(*start))
+                        ++start;
+                    break;
+            }
+        }
+        return out;
+    }
+
+    template <typename octet_iterator, typename output_iterator>
+    inline output_iterator replace_invalid(octet_iterator start, octet_iterator end, output_iterator out)
+    {
+        static const uint32_t replacement_marker = utf8::internal::mask16(0xfffd);
+        return utf8::replace_invalid(start, end, out, replacement_marker);
+    }
+
+    template <typename octet_iterator>
+    uint32_t next(octet_iterator& it, octet_iterator end)
+    {
+        uint32_t cp = 0;
+        internal::utf_error err_code = utf8::internal::validate_next(it, end, cp);
+        switch (err_code) {
+            case internal::UTF8_OK :
+                break;
+            case internal::NOT_ENOUGH_ROOM :
+                throw not_enough_room();
+            case internal::INVALID_LEAD :
+            case internal::INCOMPLETE_SEQUENCE :
+            case internal::OVERLONG_SEQUENCE :
+                throw invalid_utf8(*it);
+            case internal::INVALID_CODE_POINT :
+                throw invalid_code_point(cp);
+        }
+        return cp;
+    }
+
+    template <typename octet_iterator>
+    uint32_t peek_next(octet_iterator it, octet_iterator end)
+    {
+        return utf8::next(it, end);
+    }
+
+    template <typename octet_iterator>
+    uint32_t prior(octet_iterator& it, octet_iterator start)
+    {
+        // can't do much if it == start
+        if (it == start)
+            throw not_enough_room();
+
+        octet_iterator end = it;
+        // Go back until we hit either a lead octet or start
+        while (utf8::internal::is_trail(*(--it)))
+            if (it == start)
+                throw invalid_utf8(*it); // error - no lead byte in the sequence
+        return utf8::peek_next(it, end);
+    }
+
+    /// Deprecated in versions that include "prior"
+    template <typename octet_iterator>
+    uint32_t previous(octet_iterator& it, octet_iterator pass_start)
+    {
+        octet_iterator end = it;
+        while (utf8::internal::is_trail(*(--it)))
+            if (it == pass_start)
+                throw invalid_utf8(*it); // error - no lead byte in the sequence
+        octet_iterator temp = it;
+        return utf8::next(temp, end);
+    }
+
+    template <typename octet_iterator, typename distance_type>
+    void advance (octet_iterator& it, distance_type n, octet_iterator end)
+    {
+        for (distance_type i = 0; i < n; ++i)
+            utf8::next(it, end);
+    }
+
+    template <typename octet_iterator>
+    typename std::iterator_traits<octet_iterator>::difference_type
+    distance (octet_iterator first, octet_iterator last)
+    {
+        typename std::iterator_traits<octet_iterator>::difference_type dist;
+        for (dist = 0; first < last; ++dist)
+            utf8::next(first, last);
+        return dist;
+    }
+
+    template <typename u16bit_iterator, typename octet_iterator>
+    octet_iterator utf16to8 (u16bit_iterator start, u16bit_iterator end, octet_iterator result)
+    {
+        while (start != end) {
+            uint32_t cp = utf8::internal::mask16(*start++);
+            // Take care of surrogate pairs first
+            if (utf8::internal::is_lead_surrogate(cp)) {
+                if (start != end) {
+                    uint32_t trail_surrogate = utf8::internal::mask16(*start++);
+                    if (utf8::internal::is_trail_surrogate(trail_surrogate))
+                        cp = (cp << 10) + trail_surrogate + internal::SURROGATE_OFFSET;
+                    else
+                        throw invalid_utf16(static_cast<uint16_t>(trail_surrogate));
+                }
+                else
+                    throw invalid_utf16(static_cast<uint16_t>(cp));
+
+            }
+            // Lone trail surrogate
+            else if (utf8::internal::is_trail_surrogate(cp))
+                throw invalid_utf16(static_cast<uint16_t>(cp));
+
+            result = utf8::append(cp, result);
+        }
+        return result;
+    }
+
+    template <typename u16bit_iterator, typename octet_iterator>
+    u16bit_iterator utf8to16 (octet_iterator start, octet_iterator end, u16bit_iterator result)
+    {
+        while (start != end) {
+            uint32_t cp = utf8::next(start, end);
+            if (cp > 0xffff) { //make a surrogate pair
+                *result++ = static_cast<uint16_t>((cp >> 10)   + internal::LEAD_OFFSET);
+                *result++ = static_cast<uint16_t>((cp & 0x3ff) + internal::TRAIL_SURROGATE_MIN);
+            }
+            else
+                *result++ = static_cast<uint16_t>(cp);
+        }
+        return result;
+    }
+
+    template <typename octet_iterator, typename u32bit_iterator>
+    octet_iterator utf32to8 (u32bit_iterator start, u32bit_iterator end, octet_iterator result)
+    {
+        while (start != end)
+            result = utf8::append(*(start++), result);
+
+        return result;
+    }
+
+    template <typename octet_iterator, typename u32bit_iterator>
+    u32bit_iterator utf8to32 (octet_iterator start, octet_iterator end, u32bit_iterator result)
+    {
+        while (start != end)
+            (*result++) = utf8::next(start, end);
+
+        return result;
+    }
+
+    // The iterator class
+    template <typename octet_iterator>
+    class iterator : public std::iterator <std::bidirectional_iterator_tag, uint32_t> {
+      octet_iterator it;
+      octet_iterator range_start;
+      octet_iterator range_end;
+      public:
+      iterator () {}
+      explicit iterator (const octet_iterator& octet_it,
+                         const octet_iterator& _range_start,
+                         const octet_iterator& _range_end) :
+               it(octet_it), range_start(_range_start), range_end(_range_end)
+      {
+          if (it < range_start || it > range_end)
+              throw std::out_of_range("Invalid utf-8 iterator position");
+      }
+      // the default "big three" are OK
+      octet_iterator base () const { return it; }
+      uint32_t operator * () const
+      {
+          octet_iterator temp = it;
+          return utf8::next(temp, range_end);
+      }
+      bool operator == (const iterator& rhs) const
+      {
+          if (range_start != rhs.range_start || range_end != rhs.range_end)
+              throw std::logic_error("Comparing utf-8 iterators defined with different ranges");
+          return (it == rhs.it);
+      }
+      bool operator != (const iterator& rhs) const
+      {
+          return !(operator == (rhs));
+      }
+      iterator& operator ++ ()
+      {
+          utf8::next(it, range_end);
+          return *this;
+      }
+      iterator operator ++ (int)
+      {
+          iterator temp = *this;
+          utf8::next(it, range_end);
+          return temp;
+      }
+      iterator& operator -- ()
+      {
+          utf8::prior(it, range_start);
+          return *this;
+      }
+      iterator operator -- (int)
+      {
+          iterator temp = *this;
+          utf8::prior(it, range_start);
+          return temp;
+      }
+    }; // class iterator
+
+} // namespace utf8
+
+#endif //header guard
+
+

src/deps/utf8-cpp/utf8/core.h

@@ -0,0 +1,329 @@
+// Copyright 2006 Nemanja Trifunovic
+
+/*
+Permission is hereby granted, free of charge, to any person or organization
+obtaining a copy of the software and accompanying documentation covered by
+this license (the "Software") to use, reproduce, display, distribute,
+execute, and transmit the Software, and to prepare derivative works of the
+Software, and to permit third-parties to whom the Software is furnished to
+do so, all subject to the following:
+
+The copyright notices in the Software and this entire statement, including
+the above license grant, this restriction and the following disclaimer,
+must be included in all copies of the Software, in whole or in part, and
+all derivative works of the Software, unless such copies or derivative
+works are solely in the form of machine-executable object code generated by
+a source language processor.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE, TITLE AND NON-INFRINGEMENT. IN NO EVENT
+SHALL THE COPYRIGHT HOLDERS OR ANYONE DISTRIBUTING THE SOFTWARE BE LIABLE
+FOR ANY DAMAGES OR OTHER LIABILITY, WHETHER IN CONTRACT, TORT OR OTHERWISE,
+ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER
+DEALINGS IN THE SOFTWARE.
+*/
+
+
+#ifndef UTF8_FOR_CPP_CORE_H_2675DCD0_9480_4c0c_B92A_CC14C027B731
+#define UTF8_FOR_CPP_CORE_H_2675DCD0_9480_4c0c_B92A_CC14C027B731
+
+#include <iterator>
+
+namespace utf8
+{
+    // The typedefs for 8-bit, 16-bit and 32-bit unsigned integers
+    // You may need to change them to match your system.
+    // These typedefs have the same names as ones from cstdint, or boost/cstdint
+    typedef unsigned char   uint8_t;
+    typedef unsigned short  uint16_t;
+    typedef unsigned int    uint32_t;
+
+// Helper code - not intended to be directly called by the library users. May be changed at any time
+namespace internal
+{
+    // Unicode constants
+    // Leading (high) surrogates: 0xd800 - 0xdbff
+    // Trailing (low) surrogates: 0xdc00 - 0xdfff
+    const uint16_t LEAD_SURROGATE_MIN  = 0xd800u;
+    const uint16_t LEAD_SURROGATE_MAX  = 0xdbffu;
+    const uint16_t TRAIL_SURROGATE_MIN = 0xdc00u;
+    const uint16_t TRAIL_SURROGATE_MAX = 0xdfffu;
+    const uint16_t LEAD_OFFSET         = LEAD_SURROGATE_MIN - (0x10000 >> 10);
+    const uint32_t SURROGATE_OFFSET    = 0x10000u - (LEAD_SURROGATE_MIN << 10) - TRAIL_SURROGATE_MIN;
+
+    // Maximum valid value for a Unicode code point
+    const uint32_t CODE_POINT_MAX      = 0x0010ffffu;
+
+    template<typename octet_type>
+    inline uint8_t mask8(octet_type oc)
+    {
+        return static_cast<uint8_t>(0xff & oc);
+    }
+    template<typename u16_type>
+    inline uint16_t mask16(u16_type oc)
+    {
+        return static_cast<uint16_t>(0xffff & oc);
+    }
+    template<typename octet_type>
+    inline bool is_trail(octet_type oc)
+    {
+        return ((utf8::internal::mask8(oc) >> 6) == 0x2);
+    }
+
+    template <typename u16>
+    inline bool is_lead_surrogate(u16 cp)
+    {
+        return (cp >= LEAD_SURROGATE_MIN && cp <= LEAD_SURROGATE_MAX);
+    }
+
+    template <typename u16>
+    inline bool is_trail_surrogate(u16 cp)
+    {
+        return (cp >= TRAIL_SURROGATE_MIN && cp <= TRAIL_SURROGATE_MAX);
+    }
+
+    template <typename u16>
+    inline bool is_surrogate(u16 cp)
+    {
+        return (cp >= LEAD_SURROGATE_MIN && cp <= TRAIL_SURROGATE_MAX);
+    }
+
+    template <typename u32>
+    inline bool is_code_point_valid(u32 cp)
+    {
+        return (cp <= CODE_POINT_MAX && !utf8::internal::is_surrogate(cp));
+    }
+
+    template <typename octet_iterator>
+    inline typename std::iterator_traits<octet_iterator>::difference_type
+    sequence_length(octet_iterator lead_it)
+    {
+        uint8_t lead = utf8::internal::mask8(*lead_it);
+        if (lead < 0x80)
+            return 1;
+        else if ((lead >> 5) == 0x6)
+            return 2;
+        else if ((lead >> 4) == 0xe)
+            return 3;
+        else if ((lead >> 3) == 0x1e)
+            return 4;
+        else
+            return 0;
+    }
+
+    template <typename octet_difference_type>
+    inline bool is_overlong_sequence(uint32_t cp, octet_difference_type length)
+    {
+        if (cp < 0x80) {
+            if (length != 1) 
+                return true;
+        }
+        else if (cp < 0x800) {
+            if (length != 2) 
+                return true;
+        }
+        else if (cp < 0x10000) {
+            if (length != 3) 
+                return true;
+        }
+
+        return false;
+    }
+
+    enum utf_error {UTF8_OK, NOT_ENOUGH_ROOM, INVALID_LEAD, INCOMPLETE_SEQUENCE, OVERLONG_SEQUENCE, INVALID_CODE_POINT};
+
+    /// Helper for get_sequence_x
+    template <typename octet_iterator>
+    utf_error increase_safely(octet_iterator& it, octet_iterator end)
+    {
+        if (++it == end)
+            return NOT_ENOUGH_ROOM;
+
+        if (!utf8::internal::is_trail(*it))
+            return INCOMPLETE_SEQUENCE;
+        
+        return UTF8_OK;
+    }
+
+    #define UTF8_CPP_INCREASE_AND_RETURN_ON_ERROR(IT, END) {utf_error ret = increase_safely(IT, END); if (ret != UTF8_OK) return ret;}    
+
+    /// get_sequence_x functions decode utf-8 sequences of the length x
+    template <typename octet_iterator>
+    utf_error get_sequence_1(octet_iterator& it, octet_iterator end, uint32_t& code_point)
+    {
+        if (it == end)
+            return NOT_ENOUGH_ROOM;
+
+        code_point = utf8::internal::mask8(*it);
+
+        return UTF8_OK;
+    }
+
+    template <typename octet_iterator>
+    utf_error get_sequence_2(octet_iterator& it, octet_iterator end, uint32_t& code_point)
+    {
+        if (it == end) 
+            return NOT_ENOUGH_ROOM;
+        
+        code_point = utf8::internal::mask8(*it);
+
+        UTF8_CPP_INCREASE_AND_RETURN_ON_ERROR(it, end)
+
+        code_point = ((code_point << 6) & 0x7ff) + ((*it) & 0x3f);
+
+        return UTF8_OK;
+    }
+
+    template <typename octet_iterator>
+    utf_error get_sequence_3(octet_iterator& it, octet_iterator end, uint32_t& code_point)
+    {
+        if (it == end)
+            return NOT_ENOUGH_ROOM;
+            
+        code_point = utf8::internal::mask8(*it);
+
+        UTF8_CPP_INCREASE_AND_RETURN_ON_ERROR(it, end)
+
+        code_point = ((code_point << 12) & 0xffff) + ((utf8::internal::mask8(*it) << 6) & 0xfff);
+
+        UTF8_CPP_INCREASE_AND_RETURN_ON_ERROR(it, end)
+
+        code_point += (*it) & 0x3f;
+
+        return UTF8_OK;
+    }
+
+    template <typename octet_iterator>
+    utf_error get_sequence_4(octet_iterator& it, octet_iterator end, uint32_t& code_point)
+    {
+        if (it == end)
+           return NOT_ENOUGH_ROOM;
+
+        code_point = utf8::internal::mask8(*it);
+
+        UTF8_CPP_INCREASE_AND_RETURN_ON_ERROR(it, end)
+
+        code_point = ((code_point << 18) & 0x1fffff) + ((utf8::internal::mask8(*it) << 12) & 0x3ffff);
+
+        UTF8_CPP_INCREASE_AND_RETURN_ON_ERROR(it, end)
+
+        code_point += (utf8::internal::mask8(*it) << 6) & 0xfff;
+
+        UTF8_CPP_INCREASE_AND_RETURN_ON_ERROR(it, end)
+
+        code_point += (*it) & 0x3f;
+
+        return UTF8_OK;
+    }
+
+    #undef UTF8_CPP_INCREASE_AND_RETURN_ON_ERROR
+
+    template <typename octet_iterator>
+    utf_error validate_next(octet_iterator& it, octet_iterator end, uint32_t& code_point)
+    {
+        // Save the original value of it so we can go back in case of failure
+        // Of course, it does not make much sense with i.e. stream iterators
+        octet_iterator original_it = it;
+
+        uint32_t cp = 0;
+        // Determine the sequence length based on the lead octet
+        typedef typename std::iterator_traits<octet_iterator>::difference_type octet_difference_type;
+        const octet_difference_type length = utf8::internal::sequence_length(it);
+
+        // Get trail octets and calculate the code point
+        utf_error err = UTF8_OK;
+        switch (length) {
+            case 0: 
+                return INVALID_LEAD;
+            case 1:
+                err = utf8::internal::get_sequence_1(it, end, cp);
+                break;
+            case 2:
+                err = utf8::internal::get_sequence_2(it, end, cp);
+            break;
+            case 3:
+                err = utf8::internal::get_sequence_3(it, end, cp);
+            break;
+            case 4:
+                err = utf8::internal::get_sequence_4(it, end, cp);
+            break;
+        }
+
+        if (err == UTF8_OK) {
+            // Decoding succeeded. Now, security checks...
+            if (utf8::internal::is_code_point_valid(cp)) {
+                if (!utf8::internal::is_overlong_sequence(cp, length)){
+                    // Passed! Return here.
+                    code_point = cp;
+                    ++it;
+                    return UTF8_OK;
+                }
+                else
+                    err = OVERLONG_SEQUENCE;
+            }
+            else 
+                err = INVALID_CODE_POINT;
+        }
+
+        // Failure branch - restore the original value of the iterator
+        it = original_it;
+        return err;
+    }
+
+    template <typename octet_iterator>
+    inline utf_error validate_next(octet_iterator& it, octet_iterator end) {
+        uint32_t ignored;
+        return utf8::internal::validate_next(it, end, ignored);
+    }
+
+} // namespace internal
+
+    /// The library API - functions intended to be called by the users
+
+    // Byte order mark
+    const uint8_t bom[] = {0xef, 0xbb, 0xbf};
+
+    template <typename octet_iterator>
+    octet_iterator find_invalid(octet_iterator start, octet_iterator end)
+    {
+        octet_iterator result = start;
+        while (result != end) {
+            utf8::internal::utf_error err_code = utf8::internal::validate_next(result, end);
+            if (err_code != internal::UTF8_OK)
+                return result;
+        }
+        return result;
+    }
+
+    template <typename octet_iterator>
+    inline bool is_valid(octet_iterator start, octet_iterator end)
+    {
+        return (utf8::find_invalid(start, end) == end);
+    }
+
+    template <typename octet_iterator>
+    inline bool starts_with_bom (octet_iterator it, octet_iterator end)
+    {
+        return (
+            ((it != end) && (utf8::internal::mask8(*it++)) == bom[0]) &&
+            ((it != end) && (utf8::internal::mask8(*it++)) == bom[1]) &&
+            ((it != end) && (utf8::internal::mask8(*it))   == bom[2])
+           );
+    }
+	
+    //Deprecated in release 2.3 
+    template <typename octet_iterator>
+    inline bool is_bom (octet_iterator it)
+    {
+        return (
+            (utf8::internal::mask8(*it++)) == bom[0] &&
+            (utf8::internal::mask8(*it++)) == bom[1] &&
+            (utf8::internal::mask8(*it))   == bom[2]
+           );
+    }
+} // namespace utf8
+
+#endif // header guard
+
+

src/deps/utf8-cpp/utf8/unchecked.h

@@ -0,0 +1,228 @@
+// Copyright 2006 Nemanja Trifunovic
+
+/*
+Permission is hereby granted, free of charge, to any person or organization
+obtaining a copy of the software and accompanying documentation covered by
+this license (the "Software") to use, reproduce, display, distribute,
+execute, and transmit the Software, and to prepare derivative works of the
+Software, and to permit third-parties to whom the Software is furnished to
+do so, all subject to the following:
+
+The copyright notices in the Software and this entire statement, including
+the above license grant, this restriction and the following disclaimer,
+must be included in all copies of the Software, in whole or in part, and
+all derivative works of the Software, unless such copies or derivative
+works are solely in the form of machine-executable object code generated by
+a source language processor.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE, TITLE AND NON-INFRINGEMENT. IN NO EVENT
+SHALL THE COPYRIGHT HOLDERS OR ANYONE DISTRIBUTING THE SOFTWARE BE LIABLE
+FOR ANY DAMAGES OR OTHER LIABILITY, WHETHER IN CONTRACT, TORT OR OTHERWISE,
+ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER
+DEALINGS IN THE SOFTWARE.
+*/
+
+
+#ifndef UTF8_FOR_CPP_UNCHECKED_H_2675DCD0_9480_4c0c_B92A_CC14C027B731
+#define UTF8_FOR_CPP_UNCHECKED_H_2675DCD0_9480_4c0c_B92A_CC14C027B731
+
+#include "core.h"
+
+namespace utf8
+{
+    namespace unchecked 
+    {
+        template <typename octet_iterator>
+        octet_iterator append(uint32_t cp, octet_iterator result)
+        {
+            if (cp < 0x80)                        // one octet
+                *(result++) = static_cast<uint8_t>(cp);  
+            else if (cp < 0x800) {                // two octets
+                *(result++) = static_cast<uint8_t>((cp >> 6)          | 0xc0);
+                *(result++) = static_cast<uint8_t>((cp & 0x3f)        | 0x80);
+            }
+            else if (cp < 0x10000) {              // three octets
+                *(result++) = static_cast<uint8_t>((cp >> 12)         | 0xe0);
+                *(result++) = static_cast<uint8_t>(((cp >> 6) & 0x3f) | 0x80);
+                *(result++) = static_cast<uint8_t>((cp & 0x3f)        | 0x80);
+            }
+            else {                                // four octets
+                *(result++) = static_cast<uint8_t>((cp >> 18)         | 0xf0);
+                *(result++) = static_cast<uint8_t>(((cp >> 12) & 0x3f)| 0x80);
+                *(result++) = static_cast<uint8_t>(((cp >> 6) & 0x3f) | 0x80);
+                *(result++) = static_cast<uint8_t>((cp & 0x3f)        | 0x80);
+            }
+            return result;
+        }
+
+        template <typename octet_iterator>
+        uint32_t next(octet_iterator& it)
+        {
+            uint32_t cp = utf8::internal::mask8(*it);
+            typename std::iterator_traits<octet_iterator>::difference_type length = utf8::internal::sequence_length(it);
+            switch (length) {
+                case 1:
+                    break;
+                case 2:
+                    it++;
+                    cp = ((cp << 6) & 0x7ff) + ((*it) & 0x3f);
+                    break;
+                case 3:
+                    ++it; 
+                    cp = ((cp << 12) & 0xffff) + ((utf8::internal::mask8(*it) << 6) & 0xfff);
+                    ++it;
+                    cp += (*it) & 0x3f;
+                    break;
+                case 4:
+                    ++it;
+                    cp = ((cp << 18) & 0x1fffff) + ((utf8::internal::mask8(*it) << 12) & 0x3ffff);                
+                    ++it;
+                    cp += (utf8::internal::mask8(*it) << 6) & 0xfff;
+                    ++it;
+                    cp += (*it) & 0x3f; 
+                    break;
+            }
+            ++it;
+            return cp;        
+        }
+
+        template <typename octet_iterator>
+        uint32_t peek_next(octet_iterator it)
+        {
+            return utf8::unchecked::next(it);    
+        }
+
+        template <typename octet_iterator>
+        uint32_t prior(octet_iterator& it)
+        {
+            while (utf8::internal::is_trail(*(--it))) ;
+            octet_iterator temp = it;
+            return utf8::unchecked::next(temp);
+        }
+
+        // Deprecated in versions that include prior, but only for the sake of consistency (see utf8::previous)
+        template <typename octet_iterator>
+        inline uint32_t previous(octet_iterator& it)
+        {
+            return utf8::unchecked::prior(it);
+        }
+
+        template <typename octet_iterator, typename distance_type>
+        void advance (octet_iterator& it, distance_type n)
+        {
+            for (distance_type i = 0; i < n; ++i)
+                utf8::unchecked::next(it);
+        }
+
+        template <typename octet_iterator>
+        typename std::iterator_traits<octet_iterator>::difference_type
+        distance (octet_iterator first, octet_iterator last)
+        {
+            typename std::iterator_traits<octet_iterator>::difference_type dist;
+            for (dist = 0; first < last; ++dist) 
+                utf8::unchecked::next(first);
+            return dist;
+        }
+
+        template <typename u16bit_iterator, typename octet_iterator>
+        octet_iterator utf16to8 (u16bit_iterator start, u16bit_iterator end, octet_iterator result)
+        {       
+            while (start != end) {
+                uint32_t cp = utf8::internal::mask16(*start++);
+            // Take care of surrogate pairs first
+                if (utf8::internal::is_lead_surrogate(cp)) {
+                    uint32_t trail_surrogate = utf8::internal::mask16(*start++);
+                    cp = (cp << 10) + trail_surrogate + internal::SURROGATE_OFFSET;
+                }
+                result = utf8::unchecked::append(cp, result);
+            }
+            return result;         
+        }
+
+        template <typename u16bit_iterator, typename octet_iterator>
+        u16bit_iterator utf8to16 (octet_iterator start, octet_iterator end, u16bit_iterator result)
+        {
+            while (start < end) {
+                uint32_t cp = utf8::unchecked::next(start);
+                if (cp > 0xffff) { //make a surrogate pair
+                    *result++ = static_cast<uint16_t>((cp >> 10)   + internal::LEAD_OFFSET);
+                    *result++ = static_cast<uint16_t>((cp & 0x3ff) + internal::TRAIL_SURROGATE_MIN);
+                }
+                else
+                    *result++ = static_cast<uint16_t>(cp);
+            }
+            return result;
+        }
+
+        template <typename octet_iterator, typename u32bit_iterator>
+        octet_iterator utf32to8 (u32bit_iterator start, u32bit_iterator end, octet_iterator result)
+        {
+            while (start != end)
+                result = utf8::unchecked::append(*(start++), result);
+
+            return result;
+        }
+
+        template <typename octet_iterator, typename u32bit_iterator>
+        u32bit_iterator utf8to32 (octet_iterator start, octet_iterator end, u32bit_iterator result)
+        {
+            while (start < end)
+                (*result++) = utf8::unchecked::next(start);
+
+            return result;
+        }
+
+        // The iterator class
+        template <typename octet_iterator>
+          class iterator : public std::iterator <std::bidirectional_iterator_tag, uint32_t> { 
+            octet_iterator it;
+            public:
+            iterator () {}
+            explicit iterator (const octet_iterator& octet_it): it(octet_it) {}
+            // the default "big three" are OK
+            octet_iterator base () const { return it; }
+            uint32_t operator * () const
+            {
+                octet_iterator temp = it;
+                return utf8::unchecked::next(temp);
+            }
+            bool operator == (const iterator& rhs) const 
+            { 
+                return (it == rhs.it);
+            }
+            bool operator != (const iterator& rhs) const
+            {
+                return !(operator == (rhs));
+            }
+            iterator& operator ++ () 
+            {
+                ::std::advance(it, utf8::internal::sequence_length(it));
+                return *this;
+            }
+            iterator operator ++ (int)
+            {
+                iterator temp = *this;
+                ::std::advance(it, utf8::internal::sequence_length(it));
+                return temp;
+            }  
+            iterator& operator -- ()
+            {
+                utf8::unchecked::prior(it);
+                return *this;
+            }
+            iterator operator -- (int)
+            {
+                iterator temp = *this;
+                utf8::unchecked::prior(it);
+                return temp;
+            }
+          }; // class iterator
+
+    } // namespace utf8::unchecked
+} // namespace utf8 
+
+
+#endif // header guard
+